simulation-backed-publisher

Use this skill whenever a user wants to test content variants before publishing to find which one will get cited most by AI models — whether they say "which version of this content will perform better", "test this article before we publish", "simulate how AI will respond to this content", "which angle should we use", "generate content variants and pick the winner", "run a simulation before publishing", or any variation where the goal is data-driven content selection rather than gut-feel publishing. This skill takes an identified content opportunity, generates 2–3 distinct variants with different angles or structures, scores them against actual AI model responses from AI Visibility, references the Simulate Changes feature for pre-publish validation, and produces a clear recommendation on which variant to publish — then pushes the winner to CMS. Trigger on any mention of "simulate", "test variants", "which performs better", "A/B content", or "before we publish".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, highly actionable workflow with clear sequencing, explicit checkpoints, and concrete tool calls. Its weaknesses are mild verbosity in the framing/rationale prose and the absence of any reference files to offload the inline CMS reference material.

Suggestions

Trim the opening narrative ('You're helping a content team stop guessing...') and the closing 'Why simulate before publishing' rationale, or move them to a reference file, to reduce tokens that don't advance the workflow.

Extract the CMS tool-pattern discovery table (Step 0) and the per-CMS push instructions (Step 7) into a references/cms-guide.md file, keeping SKILL.md as a concise overview with a one-level-deep pointer.

Tighten explanatory asides like 'Small rewrites don't help you learn anything; genuine alternatives do' to directive guidance, since Claude can infer the rationale from the scoring rubric.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and skill-specific, but includes non-essential narration such as the opening ('You're helping a content team stop guessing...') and closing rationale section ('Every piece of content is a bet...') plus a few explanatory asides that could be trimmed.	2 / 3
Actionability	Highly actionable with specific MCP tool calls, exact CMS create calls with named parameters and fields, a concrete 1-5 scoring rubric per dimension, a sample score table, and ready-to-read prompt scripts — copy-paste ready guidance.	3 / 3
Workflow Clarity	Clearly sequenced Steps 0-7 with explicit validation checkpoints (confirm opportunity before variants, Simulate Changes checkpoint with a branch) and safety guards ('Never use publish_documents without explicit instruction', 'Leave published: false', Markdown fallback), plus a feedback loop for revised variants.	3 / 3
Progressive Disclosure	Well-organized with clear section headers, but no bundle/reference files exist and inline reference material (the full CMS tool-pattern table and per-CMS push instructions) that could plausibly live in a separate reference file is kept inline, so it is not a clean overview-pointing-to-details split.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is excellent: it states concrete capabilities, provides abundant natural trigger phrasings, answers both 'what' and 'when' explicitly, and carves out a distinct niche unlikely to conflict with other skills. It is thorough without resorting to vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'generates 2-3 distinct variants', 'scores them against actual AI model responses', 'references the Simulate Changes feature', 'produces a clear recommendation', 'pushes the winner to CMS' — matching the score-3 anchor for comprehensive specific actions.	3 / 3
Completeness	Explicitly answers both what (generate, score, recommend, push to CMS) and when ('Use this skill whenever a user wants...', 'Trigger on any mention of...'), with explicit trigger guidance on both ends.	3 / 3
Trigger Term Quality	Rich natural phrasings users would say ('which version of this content will perform better', 'test this article before we publish', 'simulate how AI will respond') plus short triggers ('simulate', 'test variants', 'A/B content', 'before we publish'), giving strong coverage of natural variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (simulation-backed content selection against AI model citation) with distinct triggers unlikely to overlap with generic publishing or SEO skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: amplitude/builder-skills
Commit: 22b0634

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.